1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
|
//! Code (text) is a construct that occurs in the [text][] content type.
//!
//! It forms with the following BNF:
//!
//! ```bnf
//! ; Restriction: the number of markers in the closing sequence must be equal
//! ; to the number of markers in the opening sequence.
//! code_text ::= sequence 1*code sequence
//!
//! sequence ::= 1*'`'
//! ```
//!
//! The above grammar shows that it is not possible to create empty code.
//! It is possible to include grave accents (ticks) in code, by wrapping it
//! in bigger or smaller sequences:
//!
//! ```markdown
//! Include more: `a``b` or include less: ``a`b``.
//! ```
//!
//! When turning markdown into HTML, each line ending is turned into a space.
//!
//! It is also possible to include just one grave accent (tick):
//!
//! ```markdown
//! Include just one: `` ` ``.
//! ```
//!
//! Sequences are “gready”, in that they cannot be preceded or succeeded by
//! more grave accents (ticks).
//! To illustrate:
//!
//! ```markdown
//! Not code: ``x`.
//!
//! Not code: `x``.
//!
//! Escapes work, this is code: \``x`.
//!
//! Escapes work, this is code: `x`\`.
//! ```
//!
//! Yields:
//!
//! ```html
//! <p>Not code: ``x`.</p>
//! <p>Not code: `x``.</p>
//! <p>Escapes work, this is code: `<code>x</code>.</p>
//! <p>Escapes work, this is code: <code>x</code>`.</p>
//! ```
//!
//! That is because, when turning markdown into HTML, the first and last space,
//! if both exist and there is also a non-space in the code, are removed.
//! Line endings, at that stage, are considered as spaces.
//!
//! Code (text) relates to the `<code>` element in HTML.
//! See [*§ 4.5.15 The `code` element*][html-code] in the HTML spec for more
//! info.
//!
//! In markdown, it is possible to create code with the
//! [code (fenced)][code_fenced] or [code (indented)][code_indented] constructs
//! in the [flow][] content type.
//! Compared to code (indented), fenced code is more explicit and more similar
//! to code (text), and it has support for specifying the programming language
//! that the code is in, so it is recommended to use that instead of indented
//! code.
//!
//! ## Tokens
//!
//! * [`CodeText`][Name::CodeText]
//! * [`CodeTextData`][Name::CodeTextData]
//! * [`CodeTextSequence`][Name::CodeTextSequence]
//! * [`LineEnding`][Name::LineEnding]
//!
//! ## References
//!
//! * [`code-text.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/code-text.js)
//! * [*§ 6.1 Code spans* in `CommonMark`](https://spec.commonmark.org/0.30/#code-spans)
//!
//! [flow]: crate::construct::flow
//! [text]: crate::construct::text
//! [code_indented]: crate::construct::code_indented
//! [code_fenced]: crate::construct::code_fenced
//! [html-code]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-code-element
use crate::event::Name;
use crate::state::{Name as StateName, State};
use crate::tokenizer::Tokenizer;
/// Start of code (text).
///
/// ```markdown
/// > | `a`
/// ^
/// > | \`a`
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'`')
if tokenizer.parse_state.constructs.code_text
&& (tokenizer.previous != Some(b'`')
|| (!tokenizer.events.is_empty()
&& tokenizer.events[tokenizer.events.len() - 1].name
== Name::CharacterEscape)) =>
{
tokenizer.enter(Name::CodeText);
tokenizer.enter(Name::CodeTextSequence);
State::Retry(StateName::CodeTextSequenceOpen)
}
_ => State::Nok,
}
}
/// In opening sequence.
///
/// ```markdown
/// > | `a`
/// ^
/// ```
pub fn sequence_open(tokenizer: &mut Tokenizer) -> State {
if let Some(b'`') = tokenizer.current {
tokenizer.tokenize_state.size += 1;
tokenizer.consume();
State::Next(StateName::CodeTextSequenceOpen)
} else {
tokenizer.exit(Name::CodeTextSequence);
State::Retry(StateName::CodeTextBetween)
}
}
/// Between something and something else
///
/// ```markdown
/// > | `a`
/// ^^
/// ```
pub fn between(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None => {
tokenizer.tokenize_state.size = 0;
State::Nok
}
Some(b'\n') => {
tokenizer.enter(Name::LineEnding);
tokenizer.consume();
tokenizer.exit(Name::LineEnding);
State::Next(StateName::CodeTextBetween)
}
Some(b'`') => {
tokenizer.enter(Name::CodeTextSequence);
State::Retry(StateName::CodeTextSequenceClose)
}
_ => {
tokenizer.enter(Name::CodeTextData);
State::Retry(StateName::CodeTextData)
}
}
}
/// In data.
///
/// ```markdown
/// > | `a`
/// ^
/// ```
pub fn data(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n' | b'`') => {
tokenizer.exit(Name::CodeTextData);
State::Retry(StateName::CodeTextBetween)
}
_ => {
tokenizer.consume();
State::Next(StateName::CodeTextData)
}
}
}
/// In closing sequence.
///
/// ```markdown
/// > | `a`
/// ^
/// ```
pub fn sequence_close(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'`') => {
tokenizer.tokenize_state.size_b += 1;
tokenizer.consume();
State::Next(StateName::CodeTextSequenceClose)
}
_ => {
if tokenizer.tokenize_state.size == tokenizer.tokenize_state.size_b {
tokenizer.exit(Name::CodeTextSequence);
tokenizer.exit(Name::CodeText);
tokenizer.tokenize_state.size = 0;
tokenizer.tokenize_state.size_b = 0;
State::Ok
} else {
let index = tokenizer.events.len();
tokenizer.exit(Name::CodeTextSequence);
// More or less accents: mark as data.
tokenizer.events[index - 1].name = Name::CodeTextData;
tokenizer.events[index].name = Name::CodeTextData;
tokenizer.tokenize_state.size_b = 0;
State::Retry(StateName::CodeTextBetween)
}
}
}
}
|
